Install Extras Matrix

indx keeps its core tiny and installs everything heavy or cloud-bound as an optional extra. This page is the authoritative list of every extra, the component slot it serves, the implementation(s) it unlocks, and the packages it pulls in.

The guiding rule: pip install indx must stay light: no cloud SDKs, no vector-DB clients, and no heavy parsing toolchains in core. Anything expensive is opt-in. The documented model defaults use cloud adapters when their extras are installed, while the local profile remains explicitly available for air-gapped runs. See Installation for the practical install paths and Registry & Defaults for how names like parser = "docling" resolve to these implementations.

What the bare install pulls

A plain pip install indx carries only a small set of pure-Python (and one compiled-wheel) dependencies:

Package	Why it’s in core
Pydantic v2	All boundary-crossing data models (config, manifest, documents, chunks, relations)
Typer	Builds the typed CLI command tree
Rich	Terminal rendering — progress bars, tables for indx inspect, tracebacks
Click	Underlies Typer’s parsing and completion
pydantic-settings	Layers config sources: defaults → indx.toml → env vars → CLI flags

TOML parsing needs no dependency: tomllib is in the Python standard library from 3.11 onward (indx requires Python 3.11–3.13).

pydantic-core is a wheel

Pydantic v2 brings in the compiled pydantic-core. It is small, has wheels for every supported platform, and is load-bearing for the correctness of every serialized artifact, so it stays in core rather than behind an extra.

Zero-dependency fallbacks (ship in core)

The bare install is not just a skeleton — it ships working fallbacks for every slot that would otherwise require an extra, so a full end-to-end run is possible completely offline with nothing but pip install indx:

Slot	Fallback (in core)	Behaviour
parser	plaintext	Reads files as plain text — no Docling/Torch needed
store	jsonl	Vectors and metadata written inline; brute-force linear search
vlm	none	Skips vision enrichment entirely (this is also the default VLM)
output writer	.indx and jsonl	Self-contained archive, or newline-delimited documents/chunks

Air-gapped by design

With the plaintext parser and jsonl store, indx <dir> --out <dir> produces a usable knowledge space with no database installed and no network access. For richer parsing, real ANN search, or LLM enrichment, add the relevant extras below. See the Local & air-gapped guide.

The full extras matrix

pyproject.toml ([project.optional-dependencies]) maps each extra to the packages its implementation needs. The “Pulls” column is illustrative of the headline dependency each extra brings in.

pip install …	Slot	Implementation(s) enabled	Pulls (illustrative)
indx[docling]	parser	DoclingParser	docling
indx[unstructured]	parser	UnstructuredParser	unstructured
indx[llamaparse]	parser	LlamaParseParser	llama-parse
indx[markitdown]	parser	MarkItDownParser	markitdown
indx[ollama]	llm / vlm	OllamaLLM	ollama
indx[vllm]	llm	VLLMClient	vllm, openai (OpenAI-compatible API)
indx[openai]	llm / vlm / embed	OpenAILLM, GPT4oVLM, OpenAIEmbedder	openai
indx[anthropic]	llm	AnthropicLLM	anthropic
indx[azure]	llm	AzureOpenAILLM	openai (Azure endpoint config)
indx[qwen-vl]	vlm	QwenVLClient	transformers, torch, qwen-vl-utils
indx[vlm-local]	vlm	LocalVLM	httpx
indx[bge]	embed	BGEM3Embedder (name: bge-m3)	FlagEmbedding, torch
indx[e5]	embed	E5Embedder	sentence-transformers, torch
indx[cohere]	embed	CohereEmbedder	cohere
indx[qdrant]	store	QdrantStore	qdrant-client
indx[pgvector]	store	PgVectorStore	psycopg[binary], pgvector
indx[chroma]	store	ChromaStore	chromadb
indx[lancedb]	store	LanceDBStore	lancedb
indx[langchain]	output	LangChainWriter	langchain-core
indx[llamaindex]	output	LlamaIndexWriter	llama-index-core
indx[local] / indx[defaults]	bundle	ollama + bge-m3 + qdrant (the local profile)	the local / air-gapped stack
indx[all]	bundle	everything above	union of all extras

Shared extras

A single extra can serve more than one slot when the same SDK is reused. indx[openai] enables the OpenAI LLM, the GPT-4o VLM, and the OpenAI embedder — all via the openai package. indx[ollama] covers both LLM and (where applicable) VLM use through the local Ollama runtime.

Bundles

Two convenience bundles install groups of extras in one command:

Bundle	Installs	Use when
indx[local]	ollama + bge + qdrant	You want the local profile (opt-in) — the recommended air-gapped stack — in one line.
indx[all]	The union of every extra above	CI, exploration, or trying every backend.

indx[local] and indx[defaults] are aliases for the same local bundle — install either to pull the opt-in local profile (Ollama qwen2.5, BGE-M3, Qdrant).

# Opt-in local profile (air-gapped stack): Ollama (qwen2.5), BGE-M3, Qdrant
# indx[local] and indx[defaults] are aliases for the same bundle
pip install "indx[local]"

# Everything, for CI or experimentation
pip install "indx[all]"

# Or compose exactly what you need
pip install "indx[markitdown,openai,chroma]"

Quote the bracket

Some shells (notably zsh) treat [ and ] as glob characters. Quote the spec — pip install "indx[local]" — to avoid a “no matches found” error.

Missing extras: MissingDependencyError

Because the registry only ever imports concrete implementations lazily, a missing extra never breaks an unrelated code path. The error surfaces only when you actually select that slot.

When an implementation module is imported without its extra installed, the utils.lazy.require_extra(...) helper raises a single, actionable error. For example, selecting the Qdrant store without indx[qdrant] installed yields:

MissingDependencyError: store 'qdrant' requires: pip install indx[qdrant]

The message always names the slot, the selected implementation, and the exact pip install indx[...] command to fix it. MissingDependencyError is part of the shared exception hierarchy rooted at IndxError — see Errors & exit codes.

Errors are slot-scoped, not import-scoped

Installing a plugin or selecting a default does not eagerly import every backend. If you run with the in-core plaintext parser and jsonl store, no parser/store extra is ever touched — so an air-gapped install simply never triggers a MissingDependencyError. The error appears at the moment a slot resolves to an implementation whose extra is absent.

Picking extras per slot

If you’d rather choose deliberately than install a bundle, each slot has a dedicated guide that weighs the options:

• Parsers: Choosing a parser
• LLM / VLM enrichment: Enrichment with LLM & VLM
• Embedders: Choosing an embedder
• Stores: Choosing a store
• Output writers: Output formats

For how a name in indx.toml resolves to one of these classes — and how third-party plugins register their own — see Registry & Defaults and Configuration.